330 likes | 474 Views
CIS671-Knowledge Discovery and Data Mining. AI reminders. Vasileios Megalooikonomou Dept. of Computer and Information Sciences Temple University. (based on notes by Christos Faloutsos). Agenda. Statistics AI - decision trees Problem Approach Conclusions DB. Decision Trees.
E N D
CIS671-Knowledge Discovery and Data Mining AI reminders Vasileios Megalooikonomou Dept. of Computer and Information Sciences Temple University (based on notes by Christos Faloutsos)
Agenda • Statistics • AI - decision trees • Problem • Approach • Conclusions • DB
Decision Trees • Problem: Classification - Ie., • given a training set (N tuples, with M attributes, plus a label attribute) • find rules, to predict the label for newcomers Pictorially:
Decision trees • Issues: • missing values • noise • ‘rare’ events
Decision trees • types of attributes • numerical (= continuous) - eg: ‘salary’ • ordinal (= integer) - eg.: ‘# of children’ • nominal (= categorical) - eg.: ‘car-type’
num. attr#2 (eg., chol-level) - - + + + - + - + - + - + num. attr#1 (eg., ‘age’) Decision trees • Pictorially, we have
Decision trees • and we want to label ‘?’ ? num. attr#2 (eg., chol-level) - - + + + - + - + - + - + num. attr#1 (eg., ‘age’)
Decision trees • so we build a decision tree: ? num. attr#2 (eg., chol-level) - - + + + 40 - + - + - + - + 50 num. attr#1 (eg., ‘age’)
Decision trees • so we build a decision tree: age<50 N Y chol. <40 + Y N - ...
Agenda • Statistics • AI - decision trees • Problem • Approach • Conclusions • DB
Decision trees • Typically, two steps: • tree building • tree pruning (for over-training/over-fitting)
num. attr#2 (eg.,chol-level) - - + + + - + - + - + - + num. attr#1 (eg., ‘age’) Tree building • How?
Tree building • How? • A: Partition, recursively - pseudocode: Partition ( dataset S) if all points in S have same label then return evaluate splits along each attribute A pick best split, to divide S into S1 and S2 Partition(S1); Partition(S2) • Q1: how to introduce splits along attribute Ai • Q2: how to evaluate a split?
Tree building • Q1: how to introduce splits along attribute Ai • A1: • for numerical attributes: • binary split, or • multiple split • for categorical attributes: • compute all subsets (expensive!), or • use a greedy approach
Tree building • Q1: how to introduce splits along attribute Ai • Q2: how to evaluate a split?
Tree building • Q1: how to introduce splits along attribute Ai • Q2: how to evaluate a split? • A: by how close to uniform each subset is - ie., we need a measure of uniformity:
Tree building entropy: H(p+, p-) Any other measure? p+: relative frequency of class + in S 1 0 0.5 0 1 p+
1 0 0.5 0 1 p+ Tree building entropy: H(p+, p-) ‘gini’ index: 1-p+2 - p-2 p+: relative frequency of class + in S 1 0 0.5 0 1 p+
Tree building entropy: H(p+, p-) ‘gini’ index: 1-p+2 - p-2 (How about multiple labels?)
Tree building Intuition: • entropy: #bits to encode the class label • gini: classification error, if we randomly guess ‘+’ with prob. p+
num. attr#2 (eg., chol-level) - - + + + - + - + - + - + num. attr#1 (eg., ‘age’) Tree building Thus, we choose the split that reduces entropy/classification-error the most: Eg.:
Tree building • Before split: we need (n+ + n-) * H( p+, p-) = (7+6) * H(7/13, 6/13) bits total, to encode all the class labels • After the split we need: 0 bits for the first half and (2+6) * H(2/8, 6/8) bits for the second half
Agenda • Statistics • AI - decision trees • Problem • Approach • tree building • tree pruning • Conclusions • DB
num. attr#2 (eg., chol-level) - - + + + - + - ... + - + - + num. attr#1 (eg., ‘age’) Tree pruning • What for?
num. attr#2 (eg., chol-level) - - + + + - + - ... + - + - + num. attr#1 (eg., ‘age’) Tree pruning • Q: How to do it?
Tree pruning • Q: How to do it? • A1: use a ‘training’ and a ‘testing’ set - prune nodes that improve classification in the ‘testing’ set. (Drawbacks?)
Tree pruning • Q: How to do it? • A1: use a ‘training’ and a ‘testing’ set - prune nodes that improve classification in the ‘testing’ set. (Drawbacks?) • A2: or, rely on MDL (= Minimum Description Language) - in detail:
Tree pruning • envision the problem as compression (of what?)
Tree pruning • envision the problem as compression (of what?) • and try to minimize the # bits to compress (a) the class labels AND (b) the representation of the decision tree
(MDL) • a brilliant idea - eg.: best n-degree polynomial to compress these points: • the one that minimizes (sum of errors + n)
Conclusions • Classification through trees • Building phase - splitting policies • Pruning phase (to avoid over-fitting) • Observation: classification is subtly related to compression
Reference • M. Mehta, R. Agrawal and J. Rissanen, `SLIQ: A Fast Scalable Classifier for Data Mining', Proc. of the Fifth Int'l Conference on Extending Database Technology, Avignon, France, March 1996